AI Integrations
Deploy to Buddy with your favorite AI coding agents - pipelines, sandboxes, domains and logs from your terminal or editor.
Buddy's Remote MCP Server is available.
Kiro + Buddy
Kiro is AWS's agentic IDE built around spec-driven development - it turns requirements into specs, reads across the codebase, runs commands, and edits files wherever changes are needed. Paired with Buddy, it deploys your project, triggers and monitors pipelines, ships changes across environments, and digs through build output when something needs fixing.
Kiro turns requirements into specs before it writes code, so the deployment step is something you can review in the spec before it ever runs. MCP config lives in .kiro/settings/mcp.json per workspace, or in ~/.kiro/settings/mcp.json when you want it everywhere.
Quick start
1 Install the Buddy CLInpm install -g bdy
2 Log in to Buddybdy login
3 Link your projectbdy proj link
4 Install the Buddy skillnpx skills add buddy/buddy-plugin
Open the project directory in Kiro and start the agent from the chat panel. The Buddy skill teaches it how to drive Buddy through the CLI.
Example prompts
- “Create a snake app and deploy it for me”
- “Deploy an AI chatbot with Postgres for history and Redis for rate limiting”
- “Add a pipeline that runs on every change in the repository and executes my test suite”
- “Check the last few CI pipeline runs for failures, read the logs, and fix the failing tests”
Available commands
Connect MCP
Buddy's remote MCP server exposes over 90 tools, so Kiro can run pipelines, manage deployments, and read logs straight through the API. Add the server to .kiro/settings/mcp.json in your workspace, or ~/.kiro/settings/mcp.json for all workspaces:
json{ "mcpServers": { "buddy": { "url": "https://mcp.buddy.works/mcp" } } }
Point it at the endpoint closest to your workspace region - mcp.buddy.works, mcp.eu.buddy.works or mcp.asia.buddy.works - and use the ?tools= parameter to narrow the exposed tool categories.